In partnership with
Finally, a powerful CRM—made simple.
Attio is the AI-native CRM built to scale your company from seed stage to category leader. Powerful, flexible, and intuitive to use, Attio is the CRM for the next-generation of teams.
Sync your email and calendar, and Attio instantly builds your CRM—enriching every company, contact, and interaction with actionable insights in seconds.
With Attio, AI isn’t just a feature—it’s the foundation.
Instantly find and route leads with research agents
Get real-time AI insights during customer conversations
Build AI automations for your most complex workflows
Join fast growing teams like Flatfile, Replicate, Modal, and more.
Hi!
Welcome to AIMedily.
Last Friday, I sent you an email with research and news on Large Language Models (like ChatGPT, Claude, Gemini).
There are new articles every week on that topic, and also on other specialties like cardiology, radiology, cancer, etc.
For now, I will stick to Rehab Medicine on Wednesday and LLMs on Friday.
Please let me know if you enjoy the LLMs email to keep you in the loop (no hard feelings if you prefer only the Wednesday email 📧).
And as always, please let me know what you like (and dislike) about AIMedily.
Let’s dive into today’s issue.
🤖 AIBytes
Researchers developed a soft wearable robot with a Machine Learning control system for the upper extremity.
The control modulates assistance based on user intent to move the shoulder and kinematics.
🔬 Methods
Participants: 9 subjects —5 post-stroke and 4 with amyotrophic lateral sclerosis (ALS).
The Inflatable Soft Shoulder Robot included a personalized intention detection model (IDM). (Image).
This model used information from IMUs (Inertial Measurement Units) and soft compression sensors to track movement, speed, and orientation.
The movements were classified as “UP,” “HOLD,” and “DOWN”.
The controller was programmed for each patient and assisted them depending on their shoulder angle.
Assessments:
Controller accuracy
Range of motion
Movement quality (joint angles, trunk compensation, hand-path efficiency), with and without the device.
📊 Results
The controller correctly classified shoulder movement intent with 94.2% accuracy with minimal movement.
Increased Range of motion in:
Shoulder 17.5°
Elbow 10.6°
Wrist flexion/extension by 7.6°.
Trunk compensation decreased 25.4%.
Hand-path efficiency improved 53.8%.
🔑 Key Takeaways
This wearable robot improved arm function, movement quality, and efficiency in individuals with upper limb impairment.
The machine learning controller can accurately detect user movement intent and adjust the support.
This personalized approach improved the range of motion in the upper limb and reduced trunk compensation.
🔗 Arnold J, Pathak P, Jin Y, et al. Personalized ML-based wearable robot control improves impaired arm function. Nat Commun. 2025;16:7091. https://doi.org/10.1038/s41467-025-62538-8
A scoping review to map how wearable devices and the role of AI are used for scoliosis monitoring and treatment.
🔬 Methods
Design: Scoping review following PRISMA‑ScR guidelines.
Data sources: PubMed, Scopus, Web of Science, and EMBASE (2020–2025). 88 articles met the inclusion criteria.
Wearable devices:
Sensor-Integrated Wearable and Orthotic Technologies:
3D-printed braces
Smart brace systems
Smart clothing embedded with sensors
IMU-based wearables.
EMG-based wearables.
Digital and Remote Platforms.
Integration of AI for Personalized Rehabilitation.
Sensors used:
Pressure sensors
Inertial Measurement Units (IMUs): Accelerometers and gyroscopes to track posture, gait, and spine alignment.
Surface Electromyography (sEMG) sensors: To measure muscle activity and imbalances.
Temperature sensors: Track the time the brace was used by detecting body heat.
Textile-based sensors: Integrated in clothing to monitor posture and pressure.
Capacitive and dielectric sensors – Stretchable or printed sensors that map detailed pressure distribution inside braces.
📊 Results
Wearable devices improved brace functionality and remote monitoring.
Machine learning models can measure Cobb angles from X-rays with over 92% accuracy and less than 5° error.
Custom sensors can track therapeutic exercise with 88.5% sensitivity and 100% specificity.
🔑 Key Takeaways
Wearable sensors and AI systems improve brace efficiency and enable remote monitoring.
IMUs, textile, and vision-based tools can help track posture for real-time feedback and brace control.
Wearable sensors and AI algorithms could provide accurate, non‑radiographic scoliosis monitoring.
Devices need to be validated and standardized.
🔗 Fazeli Veisari S, Bidari S, Barati K, Atlasi R, Komeili A. Wearable Devices in Scoliosis Treatment: A Scoping Review of Innovations and Challenges. Bioengineering (Basel). 2025;12(7):696. doi:10.3390/bioengineering12070696
🦾TechTool
Anara: A platform that helps you understand, organize, and write scientific documents like medical articles. You can ask questions and organize research materials. (Link).
Neurobond: A wearable device that detects volitional intention through muscle activation. Delivers stimulation to reinforce movement, promoting neuroplasticity (Link).
Ztalk.ai Break language barriers in video calls with real-time translation. Seamlessly integrate with Zoom, Google Meet, or any conferencing platform.
🧬AIMedily Snaps
👁️AI-powered mobile retina tracker screens for diabetic eye disease with 99% accuracy (Link)
🙇🏻♂️How AI is undermining the joy and effort of learning (Link).
👴 StateViewer Mayo Clinic’s AI tool identifies 9 dementia types (including Alzheimer’s) with one scan (Link).
🎙️Podcast of JAMA+ AI with David Rhew, MD from Microsoft (Link).
🧩TriviaRX
In the 18th and 19th centuries, what material (no metal) was sometimes used to stiffen body braces for posture correction?
A) Bamboo
B) Whale baleen
C) Oak wood
D) Reed grass
Now the answer from last TriviaRX ✅ C) MIT-Manus
MIT developed this robot in the early 1990s. It is one of the first robotic devices used in neurorehabilitation. Did you know the answer?
We’re done for today!
Please help me share AIMedily with your colleagues 🙂, I’d appreciate it so much.
You can:
🔄Forward this email
📲Share this link on your phone.
Thank you for helping me grow this community.
Itzel Fer, MD PM&R
Forwarded this email? Sign up here
P.S. You will get my short email on LLMs this coming Friday. 🤖
How did you like today's newsletter?
Fact-based news without bias awaits. Make 1440 your choice today.
Overwhelmed by biased news? Cut through the clutter and get straight facts with your daily 1440 digest. From politics to sports, join millions who start their day informed.
